A Model of Saliency-Based Visual Attention for Rapid Scene Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Statistical Learning of Multi-view Face Detection
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV
Automatic thumbnail cropping and its effectiveness
Proceedings of the 16th annual ACM symposium on User interface software and technology
Robust Real-Time Face Detection
International Journal of Computer Vision
MUM '05 Proceedings of the 4th international conference on Mobile and ubiquitous multimedia
Visual attention based image browsing on mobile devices
ICME '03 Proceedings of the 2003 International Conference on Multimedia and Expo - Volume 2
2006 Special Issue: Modeling attention to salient proto-objects
Neural Networks
Seam carving for content-aware image resizing
ACM SIGGRAPH 2007 papers
A smart automatic thumbnail cropping based on attention driven regions of interest extraction
Proceedings of the 2nd International Conference on Interaction Sciences: Information Technology, Culture and Human
Image retargeting through constrained growth of important rectangular partitions
PReMI'11 Proceedings of the 4th international conference on Pattern recognition and machine intelligence
Self-Adaptive Image Cropping for Small Displays
IEEE Transactions on Consumer Electronics
Enlargement or reduction of digital images with minimum loss of information
IEEE Transactions on Image Processing
An efficient method for DCT-domain image resizing with mixed field/frame-mode macroblocks
IEEE Transactions on Circuits and Systems for Video Technology
Image resizing in the compressed domain using subband DCT
IEEE Transactions on Circuits and Systems for Video Technology
A Complexity Scalable Universal DCT Domain Image Resizing Algorithm
IEEE Transactions on Circuits and Systems for Video Technology
Hi-index | 0.00 |
The problem of retargeting a larger image in a small display is to maintain recognizability of the objects. The retargeting scheme proposed in this paper provides a suitable solution to this. The input image is partitioned into rectangular strips such that alternate strips contain important or unimportant objects. Each of these rectangular strips shrinks in size to fit the entire image into the small display. Strips containing unimportant objects shrink at a higher rate than those containing important objects. It is experimentally found that this scheme performs better than many existing schemes. An estimate for the range of values for shrinkage controlling parameters is also attempted here.